• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

PPTFH:基于点对变换特征的鲁棒局部描述符用于3D表面匹配。

PPTFH: Robust Local Descriptor Based on Point-Pair Transformation Features for 3D Surface Matching.

作者信息

Wu Lang, Zhong Kai, Li Zhongwei, Zhou Ming, Hu Hongbin, Wang Congjun, Shi Yusheng

机构信息

State Key Laboratory of Materials Processing and Die & Mould Technology, School of Materials Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China.

Hubei Tri-Ring Forging Co., Ltd., Xiangyang 441700, China.

出版信息

Sensors (Basel). 2021 May 7;21(9):3229. doi: 10.3390/s21093229.

DOI:10.3390/s21093229
PMID:34066938
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8124800/
Abstract

Three-dimensional feature description for a local surface is a core technology in 3D computer vision. Existing descriptors perform poorly in terms of distinctiveness and robustness owing to noise, mesh decimation, clutter, and occlusion in real scenes. In this paper, we propose a 3D local surface descriptor using point-pair transformation feature histograms (PPTFHs) to address these challenges. The generation process of the PPTFH descriptor consists of three steps. First, a simple but efficient strategy is introduced to partition the point-pair sets on the local surface into four subsets. Then, three feature histograms corresponding to each point-pair subset are generated by the point-pair transformation features, which are computed using the proposed Darboux frame. Finally, all the feature histograms of the four subsets are concatenated into a vector to generate the overall PPTFH descriptor. The performance of the PPTFH descriptor is evaluated on several popular benchmark datasets, and the results demonstrate that the PPTFH descriptor achieves superior performance in terms of descriptiveness and robustness compared with state-of-the-art algorithms. The benefits of the PPTFH descriptor for 3D surface matching are demonstrated by the results obtained from five benchmark datasets.

摘要

局部曲面的三维特征描述是三维计算机视觉中的一项核心技术。由于真实场景中的噪声、网格简化、杂波和遮挡等因素,现有的描述符在独特性和鲁棒性方面表现不佳。在本文中,我们提出了一种使用点对变换特征直方图(PPTFH)的三维局部曲面描述符来应对这些挑战。PPTFH描述符的生成过程包括三个步骤。首先,引入一种简单但有效的策略,将局部曲面上的点对集划分为四个子集。然后,通过点对变换特征生成与每个点对子集对应的三个特征直方图,这些特征是使用所提出的达布标架计算得到的。最后,将四个子集的所有特征直方图连接成一个向量,以生成整体的PPTFH描述符。在几个流行的基准数据集上对PPTFH描述符的性能进行了评估,结果表明,与现有算法相比,PPTFH描述符在描述性和鲁棒性方面具有卓越的性能。从五个基准数据集获得的结果证明了PPTFH描述符在三维曲面匹配方面的优势。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/366cad36ce68/sensors-21-03229-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/32ca2c372257/sensors-21-03229-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/04f90810d759/sensors-21-03229-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/fd529a2a0095/sensors-21-03229-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/09e80c307023/sensors-21-03229-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/366cad36ce68/sensors-21-03229-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/32ca2c372257/sensors-21-03229-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/04f90810d759/sensors-21-03229-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/fd529a2a0095/sensors-21-03229-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/09e80c307023/sensors-21-03229-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4da3/8124800/366cad36ce68/sensors-21-03229-g005.jpg

相似文献

1
PPTFH: Robust Local Descriptor Based on Point-Pair Transformation Features for 3D Surface Matching.PPTFH:基于点对变换特征的鲁棒局部描述符用于3D表面匹配。
Sensors (Basel). 2021 May 7;21(9):3229. doi: 10.3390/s21093229.
2
Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching.评估用于三维刚性数据匹配的局部几何特征表示
IEEE Trans Image Process. 2019 Dec 17. doi: 10.1109/TIP.2019.2959236.
3
Registration of 3D point clouds using a local descriptor based on grid point normal.基于网格点法线的局部描述符对三维点云进行配准。
Appl Opt. 2021 Oct 1;60(28):8818-8828. doi: 10.1364/AO.437477.
4
Novel 3D local feature descriptor of point clouds based on spatial voxel homogenization for feature matching.基于空间体素均匀化的点云新型三维局部特征描述符用于特征匹配。
Vis Comput Ind Biomed Art. 2023 Sep 28;6(1):18. doi: 10.1186/s42492-023-00145-4.
5
Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors.基于多统计直方图描述符的 3D 点云识别与配准匹配算法。
Sensors (Basel). 2022 Jan 6;22(2):417. doi: 10.3390/s22020417.
6
Toward the Repeatability and Robustness of the Local Reference Frame for 3D Shape Matching: An Evaluation.针对 3D 形状匹配的局部参考框架的可重复性和稳健性评估。
IEEE Trans Image Process. 2018 Aug;27(8):3766-3781. doi: 10.1109/TIP.2018.2827330.
7
Advanced Planar Projection Contour (PPC): A Novel Algorithm for Local Feature Description in Point Clouds.高级平面投影轮廓(PPC):一种用于点云局部特征描述的新算法。
J Imaging. 2024 Mar 29;10(4):84. doi: 10.3390/jimaging10040084.
8
Local shape feature fusion for improved matching, pose estimation and 3D object recognition.用于改进匹配、姿态估计和3D物体识别的局部形状特征融合
Springerplus. 2016 Mar 8;5:297. doi: 10.1186/s40064-016-1906-1. eCollection 2016.
9
Shape vocabulary: a robust and efficient shape representation for shape matching.形状词汇表:一种用于形状匹配的强大而高效的形状表示。
IEEE Trans Image Process. 2014 Sep;23(9):3935-49. doi: 10.1109/TIP.2014.2336542. Epub 2014 Jul 8.
10
Efficient and accurate registration with BWPH descriptor for low-quality point clouds.使用BWPH描述符对低质量点云进行高效准确的配准。
Opt Express. 2023 Nov 6;31(23):39307-39322. doi: 10.1364/OE.505609.

引用本文的文献

1
Computer Vision for 3D Perception and Applications.计算机视觉的三维感知与应用
Sensors (Basel). 2021 Jun 8;21(12):3944. doi: 10.3390/s21123944.

本文引用的文献

1
Toward the Repeatability and Robustness of the Local Reference Frame for 3D Shape Matching: An Evaluation.针对 3D 形状匹配的局部参考框架的可重复性和稳健性评估。
IEEE Trans Image Process. 2018 Aug;27(8):3766-3781. doi: 10.1109/TIP.2018.2827330.
2
A Global Hypothesis Verification Framework for 3D Object Recognition in Clutter.用于杂乱环境中 3D 物体识别的全局假设验证框架。
IEEE Trans Pattern Anal Mach Intell. 2016 Jul;38(7):1383-1396. doi: 10.1109/TPAMI.2015.2491940. Epub 2015 Oct 16.
3
3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey.
基于局部表面特征的杂乱场景三维目标识别:综述
IEEE Trans Pattern Anal Mach Intell. 2014 Nov;36(11):2270-87. doi: 10.1109/TPAMI.2014.2316828.
4
Three-dimensional model-based object recognition and segmentation in cluttered scenes.基于三维模型的杂乱场景中的目标识别与分割
IEEE Trans Pattern Anal Mach Intell. 2006 Oct;28(10):1584-601. doi: 10.1109/TPAMI.2006.213.